© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 744
    Prev
    Next
    INDEX
    Explanations

    say Portugal

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Denver
    -34.50
     Colorado
    -30.13
    Denver
    -29.00
    Colorado
    -27.75
     Calgary
    -27.50
     Utah
    -26.25
     Wyoming
    -26.25
    常德
    -26.00
    湘西
    -26.00
     Buffalo
    -25.38
    POSITIVE LOGITS
    葡萄牙
    68.00
     Portuguese
    62.75
     Portugal
    60.50
     Lisbon
    51.50
     Portug
    50.00
    葡
    49.75
     João
    44.75
    肇庆
    39.75
     Porto
    39.00
    佛山市
    37.00
    Activations Density 0.130%

    No Known Activations